▸ NVIDIA· AMPERE

NVIDIA Jetson AGX Orin 64 GB

VRAM

64 GB

FLAGSHIP

BANDWIDTH

205

GB/S

MODELS Q4

281/331

85%

7B Q4 SPEED

~23

GOOD

▸ MODEL COVERAGE @ Q485% OF ALL

▸ ESTIMATED SPEED· BY MODEL SIZE @ Q4

Average speeds at Q4 quantization. Actual performance varies by model architecture and context length.

3B

~55

TOK/S

7B

~23

TOK/S

14B

~12

TOK/S

32B

~5

TOK/S

70B

~2

TOK/S

▸ SPECIFICATIONS

VRAM

64 GB

BANDWIDTH

205 GB/s

FP16 COMPUTE

10.7 TFLOPS

TDP

60W

MEMORY

LPDDR5

ARCHITECTURE

Ampere

CUDA CORES

2,048

TENSOR CORES

64

PCIE

Gen 4 x4

92

FAST MODELS · >30 TOK/S

Real-time chat speed

213

USABLE · >10 TOK/S

Comfortable for all tasks

281

TOTAL COMPATIBLE

Fit in VRAM at Q4

▸ RENT IT IN THE CLOUD

Buying Jetson AGX Orin 64 GB costs $15–$40k and isn’t practical for most teams. Spin one up by the hour instead:

Rent on RunPod →Or Vast.ai →

Spin up in ~60s. Pay by the second. Cancel anytime.

Some links are affiliate links — we may earn a small commission at no extra cost to you. This helps keep FitMyLLM free and independent.

▸ COMPATIBLE MODELS· 281

nomic-embed-text-v1.5 100M0.1B

EMBEDDING·8K CTX· CHAT

TOK/S · 1% VRAM

GPT-2 124M0.124B

GPT2·1K CTX· CHAT

TOK/S · 1% VRAM

SmolLM2 135M0.135B

SMOLLM·2K CTX· CHAT

TOK/S · 1% VRAM

bge-large-en-v1.5 335M0.335B

EMBEDDING·1K CTX· CHAT

TOK/S · 1% VRAM

mxbai-embed-large-v10.335B

EMBEDDING·1K CTX· EMBEDDING

TOK/S · 1% VRAM

Snowflake Arctic Embed L0.335B

EMBEDDING·1K CTX· EMBEDDING

TOK/S · 1% VRAM

GPT-2 Medium 345M0.345B

GPT2·1K CTX· CHAT

TOK/S · 1% VRAM

SmolLM2 360M0.36B

SMOLLM·8K CTX· CHAT

TOK/S · 1% VRAM

Falcon-H1 0.5B0.5B

FALCON·128K CTX· CHAT

TOK/S · 1% VRAM

Qwen 1.5 0.5B0.5B

QWEN·32K CTX· CHAT

TOK/S · 1% VRAM

Qwen 2.5 0.5B0.5B

QWEN·32K CTX· CHAT

TOK/S · 1% VRAM

EMBEDDING·8K CTX· EMBEDDING

TOK/S · 1% VRAM

QWEN·32K CTX· CHAT· REASONING

TOK/S · 1% VRAM

GPT-2 Large 774M0.774B

GPT2·1K CTX· CHAT

TOK/S · 2% VRAM

Qwen 3.5 0.8B0.8B

QWEN·256K CTX· CHAT· CODING· MULTILINGUAL

TOK/S · 2% VRAM

Qwen3.5-0.8B0.9B

QWEN·256K CTX· CHAT

TOK/S · 2% VRAM

FALCON·32K CTX· CHAT

TOK/S · 2% VRAM

INTERNLM·32K CTX· CHAT

TOK/S · 2% VRAM

TinyLlama 1.1B1.1B

LLAMA·2K CTX· CHAT

TOK/S · 2% VRAM

LFM2.5-1.2B-Thinking1.2B

LFM·122K CTX· CHAT· REASONING· TOOL_USE

TOK/S · 2% VRAM

Llama-3.2-1B1.2B

LLAMA·4K CTX· CHAT

TOK/S · 2% VRAM

DeepSeek Coder 1.3B1.3B

DEEPSEEK·16K CTX· CODING

TOK/S · 2% VRAM

EXAONE-4.0-1.2B1.3B

EXAONE·64K CTX· CHAT

TOK/S · 2% VRAM

OPT·2K CTX· CHAT

TOK/S · 2% VRAM

PHI·2K CTX· CODING

TOK/S · 2% VRAM

Phi-1.5 1.3B1.3B

PHI·2K CTX· CHAT· CODING

TOK/S · 2% VRAM

granite-4.0-h-tiny 6.9B6.9BMoE

GRANITE·128K CTX· CHAT

TOK/S · 7% VRAM

Falcon-H1 1.5B1.5B

FALCON·128K CTX· CHAT· CODING

TOK/S · 2% VRAM

GPT-2 XL 1.5B1.5B

GPT2·1K CTX· CHAT

TOK/S · 2% VRAM

Qwen2.5-Coder-1.5B1.5B

QWEN·32K CTX· CHAT· TOOL_USE· CODING

TOK/S · 2% VRAM

Qwen2 Math 1.5B1.5B

QWEN·4K CTX· REASONING

TOK/S · 2% VRAM

Qwen 2.5 1.5B1.5B

QWEN·32K CTX· CHAT· CODING

TOK/S · 2% VRAM

Yi Coder 1.5B1.5B

YI·125K CTX· CODING

TOK/S · 2% VRAM

stablelm-2-1_6b1.6B

STABLELM·4K CTX· CHAT

TOK/S · 2% VRAM

SmolLM2 1.7B1.71B

SMOLLM·8K CTX· CHAT

TOK/S · 2% VRAM

QWEN·32K CTX· CHAT· REASONING

TOK/S · 2% VRAM

Qwen 1.5 1.8B1.8B

QWEN·32K CTX· CHAT

TOK/S · 2% VRAM

Moondream2 1.9B1.9B

OTHER·2K CTX· VISION· CHAT

TOK/S · 3% VRAM

GEMMA·8K CTX· CHAT

TOK/S · 3% VRAM

Granite 3.0 2B2B

GRANITE·128K CTX· CHAT· CODING

TOK/S · 3% VRAM

▸ NEXT STEP

Get personalized recommendations.

See ranked models with benchmark scores, run commands, and precise speed estimates for your Jetson AGX Orin 64 GB.

▸Find models for Jetson AGX Orin 64 GB Compare with other GPUs

▸ DEVICE UNDER TEST

NVIDIA Jetson AGX Orin 64 GB — 64 GB VRAM.

▸ JETSON AGX ORIN 64 GB SPEC

BRAND: NVIDIA
VRAM: 64 GB LPDDR5
BANDWIDTH: 205 GB/s
FP16 COMPUTE: 10.7 TFLOPS
FP32 COMPUTE: 5.3 TFLOPS
CUDA CORES: 2,048
TENSOR CORES: 64
TDP: 60 W
ARCHITECTURE: Ampere

▸ AI CAPABILITY

281/ 331 models @ Q4

With 64 GB VRAM and 205 GB/s bandwidth, this GPU handles models up to 90B parameters.

Speed ≈ bandwidth / model_size × efficiency. A 7B model at Q4 runs at ~23 tok/s.

§ 01TOP MODELS FOR JETSON AGX ORIN 64 GB

281 FIT · SHOWING 20

MODEL	SIZE	VRAM Q4	TOK/S	AVG
Llama-3.2-90B-Vision-Instruct	90B	55.5 GB	2	48.5
Hunyuan A13B	80B	49.4 GB	13	81.1
Qwen3-Coder-Next	80B	49.4 GB	55	43.0
Qwen2.5-72B	72.7B	44.9 GB	2	39.7
Qwen2-VL 72B	72.7B	44.9 GB	2	55.5
Qwen 1.5 72B	72B	44.5 GB	2	49.7
Qwen2 Math 72B	72B	44.5 GB	2	49.7
DeepSeek R1 Distill Llama 70B	70.6B	43.6 GB	2	42.4
Llama 3.3 70B	70.6B	43.6 GB	2	44.8
Llama 3.1 70B	70.6B	43.6 GB	2	33.2
Llama 3 70B	70.6B	43.6 GB	2	44.1
Llama-3.1-Nemotron-70B	70.6B	43.6 GB	2	43.7
Cogito 70B	70B	43.3 GB	2	—
Llama 2 70B	70B	43.3 GB	2	33.4
CodeLlama 70B	70B	43.3 GB	2	45.7
Dolphin Llama 3 70B	70B	43.3 GB	2	45.7
Tulu 3 70B	70B	43.3 GB	2	59.4
WizardLM 70B	70B	43.3 GB	2	28.5
OPT 66B	66B	40.8 GB	2	—
LLaMA 1 65B	65.2B	40.3 GB	3	42.6